Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, but the description adds real substance: the output is a *draft*, generated fields are marked as suggestions with the scan as source, and no new scan is triggered. The retry sentence restates idempotentHint but usefully specifies the exact semantics ('returns the first result instead of repeating the action').

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The trigger condition is front-loaded, followed by the creation semantics and then the negative constraint. Four sentences, all earning their place, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested-body mutation tool with no output schema, the description covers intent, source, and idempotency well, but omits what the call returns (e.g., the new draft's id) that an agent would need to chain a follow-up updateIcpDraft or publishIcp call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 50% schema description coverage, only idempotencyKey is documented in the schema. The description does clarify that product_id and scan_id refer to an existing Leadpoet scan, but it says nothing about segment_id, reviewed, or name, leaving those nested body fields unexplained in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Creates a new ICP draft') and qualifies the source precisely ('from a product in a website scan you already ran in Leadpoet'). That source qualifier implicitly separates it from createIcp/createManualIcp/createIcpDraft, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Useful when the user wants an ICP from a website scan of their company' sets a clear trigger, and 'Does not run a new scan' is an explicit when-not boundary. It stops short of naming the alternative tool (createManualIcp, createIcp) for users who have no existing scan, which would have made this a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.